I just built a *functioning* React app by describing what I wanted to GPT-3. I'm still in awe.

Setting up Next.js + shadcn/ui + Drizzle + Better Auth takes 3-4 hours every single project. Same lint rules. Same Claude Code settings. Same pages. Same auth flow. Copy. Paste. Debug. Repeat. We all hate it. Sound familiar? 🧵

you will regret not using a monorepo.

hello j'ai build un CLI qui init tes projets avec framework, lib, auth, db et de ton choix avec une commande : bunx create-faster j'ai perdu trop de temps à reconfig la même chose, des heures de setup avant d'écrire la première ligne de code → github.com/plvo/create-fa… → docs:

anyone got a clean, minimalist claude code status bar with context %? mine is uggly af

make me rich daddy

ok Claude analyze X’s algorithm then completely rebrand my profile and generate content for me. Make no mistakes

The solution to anxiety is action.

maaan the /copywriting and /seo-audit skills = BANGER

Here's a 1 GB memory reduction for very long Claude Code sessions Before: `() => controller.abort()` Fix: `controller.abort.bind(controller)`

we got claude code nft minting skills before gta6

it has started…

New art project. Train and inference GPT in 243 lines of pure, dependency-free Python. This is the *full* algorithmic content of what is needed. Everything else is just for efficiency. I cannot simplify this any further. gist.github.com/karpathy/8627f…

just got my (naked 🫣) Lucky Hypio Winners ? Hypio zee.hype